DeepLab is a deep learning model for semantic image segmentation, where the goal is to assign semantic labels to every pixel in the input image.
Questions tagged [deeplab]
130 questions
1
vote
1 answer
How to create a Keras model using a frozen_interference_graph.pb?
I want to use a pre-trained model and add a segmentation head at the end of that, but the problem is that I just have the 'frozen_inference_graph.pb'. These are the files that I have from the model:
I have tried several ways:
1. loading the…

malekiamir
- 119
- 2
- 11
1
vote
1 answer
Tensorflow - deeplab colormap
I'm messing with Semantic Image Segmentation from google's DeepLab . I want to be able change colors for each semantic ( i.e. person , cat etc) . The method that creates the colormap , with PASCAL benchmark is
def create_pascal_label_colormap():
…

DavidDunn
- 143
- 1
- 12
1
vote
0 answers
Deeplab new dataset not finding new class
Hey I am attempting to add a new class to the pascal dataset to make it 21 detectable classes. I have followed these steps:
Segment Images. I picked chickens and made 4 separate chicken segementations. Here's an example:
place corresponding…

jake
- 71
- 1
- 1
- 3
1
vote
1 answer
Need to start the training twice to load checkpoint (It worked, but why?)
I am modifying deeplab Network. I added a node to the mobilenet-v3 feature extractor's first layer, which reused the existing variables. As no extra parameters would be needed, I could theoretically load the old checkpoint.
Here comes the situation…

zheyuanWang
- 1,158
- 2
- 16
- 30
1
vote
1 answer
Difference between CRF and Fully Connected CRF?
Can anyone explain me the difference between Conditional Random Fields and Fully Connected Conditional Random Fields for semantic segmentation?
I only understand so far, that with CRF you try to use two kinds of information to improve the…

mAI
- 111
- 1
- 10
1
vote
0 answers
Are there any plans to migrate the deeplab code to tensorflow 2?
The deeplab code under tensorflow/models/research/deeplab seems to be using the older version of tensorflow. With the new version of tensorflow out, are there any plans to migrate the existing repo to use tf2, specifically the tf2.keras api for…

bossman
- 340
- 2
- 17
1
vote
0 answers
About the Deeplab output all black(0) output
I want to ask the problem about Deeplab with mobilenetv2 output all black(0) array, and confirm it is all zero not 0~1. I have seen so many people have the same problem, but I couldn't find the solution yet.
1. My segmentation data is 1D…

icoicqico
- 21
- 4
1
vote
1 answer
Training my own dataset on deeplab but inference all black
I try to train my own dataset on deeplab model in TensorFlow model garden, I could get a decreasing loss result through time, I using pre-train model provided by official repo.
But when I try to vis with latest checkpoint or try to freeze the model…

邓剑波
- 11
- 1
1
vote
2 answers
DeeplabV3 MobileNetV2 Quantization for USB Coral TPU with custom input size ((100, 100) rather than (513, 513))
I have been following the steps in https://github.com/tensorflow/models/blob/394baa9f21424d3522ccfbdcee8acd3840891ff6/research/deeplab/g3doc/quantize.md to quantize a DeeplabV3 MobileNetV2 model for the USB Coral TPU but I cannot get it to…

Saturnin Pugnet
- 394
- 2
- 8
1
vote
1 answer
Error converting dataset to tfrecord for DeepLab v3+
I'm trying to convert a custom dataset to tfrecord for DeepLab v3+, following this tutorial. My directory setup is as follows:
+ datasets
+ pascal_voc_seg/custom_dataset
+ VOCdevkit
+ VOC2012
+ JPEGImages
+…

NiallD
- 23
- 3
1
vote
1 answer
which python and tensorflow version is used to train DeepLab v3+ using tensorflow api?
I have been getting multiple errors which are due to conflicts in the TensorFlow version installed in my system and the version used to write the code in Tensorflow API.
I am using python 3.6.7 and Tensorflow 2.0 to get started with the code…

Pallawi.ds
- 103
- 1
- 7
1
vote
0 answers
streaming mean iou DeepLabv3+
can someone explain me how streaming mean iou from works? I used the tensorflow research repository and their eval.py function runs everytime there is a new checkpoint. But which values does it take into account? The whole predictions since the…

vftw
- 1,547
- 3
- 22
- 51
1
vote
2 answers
Deeplab V3 installation : ModuleNotFoundError: No module named 'deeplab'
after following the instruction at:
https://github.com/mathildor/DeepLab-v3/blob/master/g3doc/installation.md
and:
echo %PYTHONPATH%
$PYTHONPATH: 'C:\.....\tensorflow\models\research' : 'C:\.....\tensorflow\models\research\slim' "
and also after…

Shay Silberklang
- 11
- 2
1
vote
1 answer
An error occurred while training deeplabv3++ using CityScapes dataset:“data split name train not recognized”
I followed the following steps:
1.CityScapes data set preparation
2.Generate TFRecords of CityScapes
3.Download the pre-training model
4.Run official instruction
python deeplab/train.py \
--logtostderr \
--training_number_of_steps=1000…

Andrew
- 11
- 1
1
vote
1 answer
Smaller output stride and bigger atrous rates produces larger heatmaps
I am using DeepLabv3+ and I am running some tests. For my first run I used an output_stride=16 and atrous_rates=[6, 12, 18] and in the 2nd run I used output_stride=8 and atrous_rates=[12,24, 36]. Then I used tensorboard to see the results and I…

vftw
- 1,547
- 3
- 22
- 51